Incremental Hopping-Window Pose-Graph Fusion for Real-Time Vehicle Localization

Das, Anweshan; Dubbelman, Gijs

doi:10.1109/vtcspring.2019.8746464

Cited by 2 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The GNSS measurements act as loop closures, which reduces dependency on imagebased landmark and feature detection algorithms. We combine and extend our previous work [29,30] on pose-graph based vehicle localization. In [29], we propose and evaluate multiple off-line pose-graph modeling strategies to fuse vehicle odometry and GNSS data for robust vehicle positioning.…”

Section: Introductionmentioning

confidence: 98%

“…In [29], we propose and evaluate multiple off-line pose-graph modeling strategies to fuse vehicle odometry and GNSS data for robust vehicle positioning. In [30], we extended our work in [29] and proposed a realtime pose-graph generation and optimization framework, "Incremental Hopping Window pose-graph Optimization" for vehicle positioning. This article extends the framework to model stereo visual odometry, vehicle odometry, and GNSS measurements into a posegraph which is then optimized using the incremental hopping window pose-graph fusion strategy [30].…”

Section: Introductionmentioning

confidence: 99%

“…In [30], we extended our work in [29] and proposed a realtime pose-graph generation and optimization framework, "Incremental Hopping Window pose-graph Optimization" for vehicle positioning. This article extends the framework to model stereo visual odometry, vehicle odometry, and GNSS measurements into a posegraph which is then optimized using the incremental hopping window pose-graph fusion strategy [30]. We also extensively compare the framework's performance with (a) vehicle odometry and GNSS fusion (b) stereo visual odometry, vehicle odometry, and GNSS fusion for real-time vehicle positioning on large datasets covering more than 180 km in different scenarios such as urban-canyons and highways.…”

Section: Introductionmentioning

confidence: 99%

“…Figure 6. The red arrows represent a window; a new window is generated at every multiple of w meters traveled by the vehicle, with all the nodes contained in the last l meters of the last optimized window, which creates a hopping effect[30].…”

mentioning

confidence: 99%

“…(a) Batch size vs. average precision plot for different window sizes (500, 1000, 1500, 2000, 2500 in meters) of all datasets[30]. (b) Batch size vs. total time plot for different window sizes.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Real-Time Vehicle Positioning and Mapping Using Graph Optimization

Das

Elfring

Dubbelman

2021

Sensors

Self Cite

View full text Add to dashboard Cite

In this work, we propose and evaluate a pose-graph optimization-based real-time multi-sensor fusion framework for vehicle positioning using low-cost automotive-grade sensors. Pose-graphs can model multiple absolute and relative vehicle positioning sensor measurements and can be optimized using nonlinear techniques. We model pose-graphs using measurements from a precise stereo camera-based visual odometry system, a robust odometry system using the in-vehicle velocity and yaw-rate sensor, and an automotive-grade GNSS receiver. Our evaluation is based on a dataset with 180 km of vehicle trajectories recorded in highway, urban, and rural areas, accompanied by postprocessed Real-Time Kinematic GNSS as ground truth. We compare the architecture’s performance with (i) vehicle odometry and GNSS fusion and (ii) stereo visual odometry, vehicle odometry, and GNSS fusion; for offline and real-time optimization strategies. The results exhibit a 20.86% reduction in the localization error’s standard deviation and a significant reduction in outliers when compared with automotive-grade GNSS receivers.

show abstract

Section: Introductionmentioning

confidence: 98%